PSO优化ELM在火灾探测中的应用

为提高火灾探测精度,避免标准ELM陷入局部最优,本文基于火灾特征值CO浓度、烟雾浓度、温度建构了一种基于粒子群(PSO)优化极限学习机(ELM)的火灾探测模型,通过PSO优化ELM输入层与隐含层权值以及偏置,利用最优值进行极限学习机网络训练,将训练好的网络对测试样本进行预测并验证方法有效性.研究显示,PSO-ELM的均...     

Application of artificial neural network for performance evaluation of vertical axis wind turbine rotor

In the present paper, artificial neural network (ANN) modelling has been performed for evaluating power coefficient (C_p) and torque coefficient (C_t) of a combined three-bucket-Savonius and three-bladed-Darrieus vertical axis wind turbine rotor, which has got potential for power generation in a small-scale manner, especially in low wind speed conditions. However, detailed experimental work on the rotor for evaluating its performance parameters is either scarce or too costly and time consuming to carry out. In this work, a new ANN modelling method is adopted to map the input–output parameters using very small training data sets, selected from past experimental results of the rotor. The trained ANN models are used to predict the performance data, which are obtained within acceptable error limits. Furthermore, to evaluate the fit values and estimate the variance of the predicted data by the ANN models, linear regression equations are fitted to the experimental and predicted results, which shows that R-squared (R²) values are obtained close to unity meaning good fitting of the data. Moreover, the results of ANN modelling are also compared with that of radial basis function (RBF) networks, which also show a good agreement between ANN predicted data and RBF network data. The present ANN models can be exploited to extract more performance data within a given range of input data.     

Multi-scale correlation analyses of two lateral profiles of full-scale downburst wind speeds

Lateral correlation analyses are carried out in different scales for two sets of full-scale thunderstorm downburst full wind speed time series. These two sets of data were recorded at the TTU field site, Texas, USA, on June 4 and 15, 2002, respectively. The same data sets were also used in the authors’ previous paper [L. Chen, C.W. Letchford, Proper orthogonal decomposition of two vertical profiles of full-scale nonstationary correlated downburst wind speeds, J. Wind Eng. Ind. Aerodyn., 93(3)(2005) 187-266.], which presents a methodology to model downburst vertical profiles. The statistical procedures utilized in [7], such as the POD technique, the wavelet shrinkage for time-varying mean inference, the two-stage weighted moving-average method for time-varying variance inference and the Priestley's EPSD estimator, are also employed in this paper and their details are thus omitted. While in [7] the authors employed the proper orthogonal decomposition (POD) to reduce the dimensions, POD in this article is employed to measure the degree of the correlation between two deterministic time series. Conventionally, wind speeds are decomposed to a time-varying mean speed and a nonstationary fluctuating speed by virtue of wavelet shrinkage [7]. Time-varying mean speeds are in the largest scale, which are essentially due to translations of storms and radial velocities of spreading flow. It was observed that the time-varying standard deviations [7] of fluctuating speeds are basically driven by time-varying mean speeds other than small-scale turbulence. Therefore, time-varying standard deviations are considered in the medium scale. Finally, the modulated fluctuating speeds are viewed in the smallest scale and due to small-scale turbulence. It is found that (1) the two lateral profiles are fully correlated and almost evenly spatially distributed in the largest and medium scales with more than 96% of the total energy; (2) they are uncorrelated in the smallest scale since the measurement locations are at least 263 m apart.     

Forecasting construction industry demand,price and productivity in Singapore: the BoxJenkins approach

In academic research, the traditional Box-Jenkins approach is widely acknowledged as a benchmark technique for univariate methods because of its structured modelling basis and acceptable forecasting performance. This study examines the versatility of this approach by applying it to analyse and forecast three distinct variables of the construction industry, namely, tender price, construction demand and productivity, based on case studies of Singapore. In order to assess the adequacy of the Box-Jenkins approach to construction industry forecasting, the models derived are evaluated on their predictive accuracy based on out-of-sample forecasts. Two measures of accuracy are adopted, the root mean-square-error (RMSE) and the mean absolute percentage error (MAPE). The conclusive findings of the study include: (1) the prediction RMSE of all three models is consistently smaller than the model's standard error, implying the models' good predictive performance; (2) the prediction MAPE of all three models consistently falls within the general acceptable limit of 10%; and (3) among the three models, the most accurate is the demand model which has the lowest MAPE, followed by the price model and the productivity model.     

Performance based design extreme wind loads on a tall building

This paper presents a procedure for the calculation of wind loads on a proposed 385 ft tall building located in strong wind and mixed strong wind and hurricane wind regions. The procedure for the computation of design wind loads uses mixed distribution and Monte Carlo simulation. The results of a probabilistic analysis of hurricane wind speeds are combined with the probability distribution of recorded extreme wind speeds (excluding hurricane data) at the site. A 50‐year sample of extreme wind speeds is created and the maximum 50‐year wind (from the hurricane and the recorded data) is noted. The simulation is repeated for a large number of samples (>10000) and the probability distribution of the 50‐year wind speed is computed for use in establishing the design wind speed Copyright © 2001 John Wiley & Sons, Ltd.     

Modeling corrosion currents of reinforced concrete using ANN

In this study, the mechanical properties of concretes are determined and the corrosion performances of steel that is embedded in concrete are analyzed by impressed voltage test. Different types of cements are used to prepare the concrete specimens with 0, 10, 20% fly ash. Corrosion currents of each specimen are measured and collected in five minute intervals using a data logger. The corrosion currents are modeled using feed forward artificial neural networks (ANNs). Measured results are then compared with the modeled ones in terms of root mean square error (RMSE), mean absolute percentage error (MAPE) and correlation coefficient criterion. It is concluded that using composite cement or fly ash instead of cement, the durability of concrete against the effects of corrosion is improved considerably. It is also concluded that using ANNs, accurate modeling results for corrosion currents can be obtained.     

The effects of wind on people; New criteria based on wind tunnel experiments

Experiments on the effects of wind on people are described. About 40 people were involved in tests in a wind tunnel at the National Physical Laboratory. The wind tunnel was specially-adapted to produce gusty winds. The volunteers performed a number of everyday tasks at wind speeds of 4 and 8·5 m/s with and without turbulence. The steadiness and direction of walking were measured when the volunteers entered the tunnel and walked up and down. Forces on the ground were also measured. Six groups of volunteers gave subjective verbal assessments of wind conditions ranging from 4 to 12·5 m/s.From the experiments we have drawn conclusions as to what kinds of wind speed, gustiness and variation of wind speed are found to be tolerable, are found to affect performance, and are found to affect the people's balance while walking. We find people to be sensitive to variation in the wind so that previous criteria for acceptable wind speeds need to be revised downwards. New criteria are proposed to enable architects and planners to use wind speed and gustines data to predict whether wind conditions are likely to be acceptable or not.     

Directional persistence of low wind speed observations

Low wind speed data is presented for stable, high-pressure sunny weather for an urban environment in the UK. In these climatologies, ventilation of buildings and dispersal of pollutants is often considered inadequate. Persistence, the length of time in which the wind blows in a specific direction and for a given angular range, is analysed. The observational data shows that in these low wind speed conditions, the wind blows in a consistent direction, for significant periods of time, and that truly calm conditions are very infrequent. The analysis of data for hot, dry, sunny and high-pressure conditions at one UK urban site, indicates that there are larger than expected air movements in these light wind scenarios. Values for mean duration of persistent wind episodes commonly exceed 30 s, with similar values for the standard deviations. The Weibull statistical structure equally applies to these low wind speed observations. In this urban environment, for 45% of the time, the persistent wind events last longer than one standard deviation above the mean. At wind speeds lower than 2 m s⁻¹, the duration of persistent wind episodes remains constant and nor does it decrease with wind speed. This may be due to larger scale meteorological influences, perhaps convective activity and eddies in the boundary layer, which create air motions in calm daytime conditions in the UK.     

Prediction of mode I fracture toughness of rock using linear multiple regression and gene expression programming

Prediction of mode I fracture toughness(KIC) of rock is of significant importance in rock engineering analyses. In this study, linear multiple regression(LMR) and gene expression programming(GEP)methods were used to provide a reliable relationship to determine mode I fracture toughness of rock. The presented model was developed based on 60 datasets taken from the previous literature. To predict fracture parameters, three mechanical parameters of rock mass including uniaxial compressive strength(...     

台风 “鲇鱼”作用下厦门沿海某超高层建筑的风场和风压特性实测研究

为研究我国沿海地区超高层建筑的风场和风压特性,在2010年台风“鲇鱼”登陆前后对厦门沿海某超高层建筑的风场和建筑表面风压进行了同步监测。通过对实测风场和风压数据的深入分析表明：沿海地区超高层建筑风场的湍流度随风速增大变化平稳,阵风因子随湍流度的增大而增大;实测脉动风速功率谱密度与von Karman谱吻合较好;建筑各面内测点之间的瞬时风压、平均风压、平均风压系数和极值风压系数具有较强的相关性;实测平均风压和平均风压系数在迎风面较大,在背风面非常小;当风从角部吹向建筑时,随着风向角的变化,两迎风面的平均风压系数随着平均风速的增大变化规律相反;两背风面的平均风压系数随着平均风速的增大逐渐减小;迎风面的极值风压系数随着风向角的变化正负波动较大,背风面的极值风压系数分布较为均匀;迎风面的脉动风压系数较大且变化较大,背风面的脉动风压系数非常小且变化平稳;建筑各面的极值风压系数和脉动风压系数的幅值随着风速的增大逐渐减小。     

Prediction of the crack condition of highway pavements using machine learning models

Departments of Transportation regularly evaluate the condition of pavements through visual inspections, nondestructive evaluations, image recognition models and learning algorithms. The above methodologies, though efficient, have drawn attention due to their subjective errors, uncertainties, noise effects and overfitting. To improve on the outcomes of the shallow learning models already used in pavement crack prediction, this paper reports on an investigation of the use of recursive partitioning and artificial neural networks (ANN; deep learning frameworks) in predicting the crack rating of pavements. Explanatory variables such as the average daily traffic and truck factor, roadway functional class, asphalt thickness, and pavement condition time series data are employed in the model formulation. Overall, it is observed that the recursive partitioning (regression tree – R² > 0.8 and classification tree – R² > 0.6) and ANN (continuous response – R² > 0.8 and categorical response – R² > 0.6) are compelling machine learning models for the prediction of the crack ratings based on their goodness-of-fit statistics, mean absolute deviation (MAD < 0.4) and the root mean square errors (RMSE between 0.30 and 0.65).     

Estimation of wind speed: A data-driven approach

A method for prediction of wind speed at a selected location based on the data collected at neighborhood locations is presented. The affinity of wind speeds measured at different locations is defined by Pearson’s correlation coefficient. Five turbines with similar wind conditions are selected among 30 wind turbines for in-depth analysis. The wind data from these turbines are used to predict wind speed at a selected location. A neural network ensemble is used to predict the value of wind speed at the turbine of interest. The models have been tested and the computational results are discussed. The results demonstrate that a higher Pearson’s correlation coefficient between the wind speeds measured at different turbines has produced better prediction accuracy for the same training and test scenario.     

Specification of the design wind load—A critical review of code concepts

In a simplified approach, the design wind load can be specified based on an appropriate small target value of the exceedance probability. For the ultimate limit state, the reasonable reference period is the projected design working life of the structure; for the serviceability limit state a suitable reference period is one year. Basically, at least the extreme wind speeds and the extremes of the aerodynamic coefficients have to be understood as random variables. Further random variables are the duration of a single storm and the relative intensity over the length of the storm. Neglecting these two parameters may lead to underestimations of the design wind load. The design values of the wind speeds are specified in codes with mainly two different concepts: either in terms of a product of the characteristic wind speed and a partial factor or directly as design value. The variable wind speed is represented in codes by gust wind speeds, by 10-min mean wind speeds or by hourly mean wind speeds. For the design value of the aerodynamic coefficient, mainly two concepts are used in codes: the mean value of the extremes or the 78%-fractile value, the latter known as ‘Cook–Mayne’ coefficient. The paper tries to sort out the differences between these approaches and tries to comment on one or the other shortcoming. Additionally, the complexity of the codification task is discussed when different wind climates have to be covered.     

Assessment of evolutionary algorithms in predicting non-deposition sediment transport

In this article, the densimetric Froude number of the flow is estimated using the parameters of volumetric sediment concentration (C_V), the relative depth of flow (d/R), dimensionless particle number (D_gr) and the overall sediment friction factor (λ_s). The particle swarm optimization (PSO) and imperialist competitive algorithms (ICA) were used to estimate the densimetric Froude number. To study the effects of sediment transport parameters on the densimetric Froude number, six different models are presented. The PSO algorithm with root mean square error (RMSE) = 0.014 and mean absolute percentage error (MAPE) = 5.1% present the results with a relatively good accuracy. The accuracy of the results presented for the selected model by the ICA algorithm is also in the form of RMSE = 0.007 and MAPE = 5.6%. Although both algorithms return good results in estimating the densimetric Froude number for the selected model, it should be mentioned that for all the six presented models ICA returns better results than PSO.     

Maximum wind speed estimation for arbitrary month periods in Japan

In order to determine the design wind speed for temporary structures or structures during construction, the seasonal variation of extreme wind speeds should be taken into account. Based on the examination of cumulative distributions of monthly maximum wind speeds recorded at 143 sites in Japan in a period between 1964 and 1979, monthly maximum wind speeds of mean recurrence intervals are presented in terms of the ratio to the annual maximum of corresponding mean recurrence intervals for typical months and various sites in Japan. Then a simple formula to evaluate extreme wind speeds for arbitrary month period is proposed and its consistency was confirmed for typical cases.     

不同风嘴形式分体箱梁桥梁的静力风致稳定性能

作为大跨径以及超大跨径桥梁一种新兴的断面形式,分体箱梁可以改善空气动力性能和提高颤振临界风速,但是还需要保证其静力风致稳定性能, 研究了不同风嘴形式下分体箱梁的静力三分力系数和静力风致稳定性能随开槽率的演变规律。结果表明：两种风嘴形式分体箱梁的阻力系数随开槽率增加而 增大,采用断面实体宽度为无量纲化标准时断面升力系数绝对值会随开槽率的增加而增加,这与采用断面总宽为无量纲化标准时结果相反,升力矩系数绝对 值会随着开槽率的增加而减小,但这种规律性会受到风攻角的影响;风嘴对称性的变化仅改变断面阻力系数随开槽率的变化规律;两种计算模型下,对称风 嘴断面分体箱梁桥梁跨中的各向位移绝对值和静力风致失稳临界风速随开槽率的变化规律完全相反,而不对称风嘴断面的各向位移变化规律相似但也有区别 ;总体上对称风嘴断面的最低静力风致失稳临界风速要高于不对称风嘴断面;考虑结构刚度变化会使断面开槽后静力风致失稳临界风速随着开槽率的增加而 升高并超过不考虑刚度变化时的相应值,故对分体箱梁静力风致稳定性能分析时需要考虑开槽率不同带来的结构刚度变化。     

Profiles of mean wind speeds and vertical turbulence intensities measured at seashore and two inland sites using Doppler sodars

The authors’ group has been conducting full-scale measurements of wind velocities with Doppler sodars. It is very important to accurately assess the profiles of mean wind speeds and turbulence intensities in relation to terrain roughness. In this study, the profiles were evaluated for all data measured over a long period at a seashore and two inland sites. It is confirmed that for strong winds the profiles can be approximated by a single power law at altitudes between 50 and 340 m. The power law exponents of the mean wind speed profiles are approximately 0.1 for wind from the sea and 0.2-0.3 for wind blown over land. Those of the turbulence intensity profiles are approximately 0 and −0.2 to 0.4, respectively.     

Comparison of machine learning methods for ground settlement prediction with different tunneling datasets

This study integrates different machine learning (ML) methods and 5-fold cross-validation (CV) method to estimate the ground maximal surface settlement (MSS) induced by tunneling. We further investigate the applicability of artificial intelligent (AI) based prediction through a comparative study of two tunnelling datasets with different sizes and features. Four different ML approaches, including support vector machine (SVM), random forest (RF), back-propagation neural network (BPNN), and deep neural network (DNN), are utilized. Two techniques, i.e. particle swarm optimization (PSO) and grid search (GS) methods, are adopted for hyperparameter optimization. To assess the reliability and efficiency of the predictions, three performance evaluation indicators, including the mean absolute error (MAE), root mean square error (RMSE), and Pearson correlation coefficient (R), are calculated. Our results indicate that proposed models can accurately and efficiently predict the settlement, while the RF model outperforms the other three methods on both datasets. The difference in model performance on two datasets (Datasets A and B) reveals the importance of data quality and quantity. Sensitivity analysis indicates that Dataset A is more significantly affected by geological conditions, while geometric characteristics play a more dominant role on Dataset B.     

Developing cation exchange capacity and soil index properties relationships using a neuro-fuzzy approach

Artificial intelligence methods are employed to predict cation exchange capacity (CEC) from five different soil index properties, namely specific surface area (SSA), liquid limit, plasticity index, activity (ACT), and clay fraction (CF). Artificial neural networks (ANNs) analyses were first employed to determine the most related index parameters with cation exchange capacity. For this purpose, 40 datasets were employed to train the network and 10 datasets were used to test it. The ANN analyses were conducted with 15 different input vector combinations using same datasets. As a result of this investigation, the ANN analyses revealed that SSA and ACT are the most effective parameters on the CEC. Next, based upon these most effective input parameters, the fuzzy logic (FL) model was developed for the CEC. In the developed FL model, triangular membership functions were employed for both the input (SSA and ACT) variables and the output variable (CEC). A total of nine Mamdani fuzzy rules were deduced from the datasets, used for the training of the ANN model. Minimization (min) inferencing, maximum (max) composition, and centroid defuzzification methods are employed for the constructed FL model. The developed FL model was then tested against the remaining datasets, which were also used for testing the ANN model. The prediction results are satisfactory with a determination coefficient, R ² = 0.94 and mean absolute error, (MAE) = 7.1.